Abstract
Aircraft trajectory prediction is a challenging problem in air traffic control, especially for conflict detection. Traditional trajectory predictors require a variety of inputs such as flight-plans, aircraft performance models, meteorological forecasts, etc. Many of these data are subjected to environmental uncertainties. Further, limited information about such inputs, especially the lack of aircraft tactical intent, makes trajectory prediction a challenging task. In this work, we propose a deep learning model that performs trajectory prediction by modeling and incorporating aircraft tactical intent. The proposed model adopts the encoder-decoder architecture and makes use of the convolutional layer as well as Gated Recurrent Units (GRUs). The proposed model does not require explicit information about aircraft performance and wind data. Results demonstrate that the provision of enriched aircraft intent, together with appropriate model design, could improve the prediction error up to 30% at a prediction horizon of 10 minutes (from 4.9 nautical miles to 3.4 nautical miles). The model also guarantees the mean error growth rate with increasing look-ahead time to be lower than 0.2 nautical miles per minute. In addition, the model offers a very low variance in the prediction, which satisfies the variance-standard specified by EUROCONTROL (EU Organization for Safety and Navigation of Air Traffic) for trajectory predictors. The proposed model also outperforms the state-of-the-art trajectory prediction model, where the Root Mean Square Error (RMSE) is reduced from 0.0203 to 0.0018 for latitude prediction, and from 0.0482 to 0.0021 for longitude prediction in a single prediction step of 15 seconds look-ahead. We showed that the pre-trained model on ADS-B data maintains its high performance, in terms of cross-track and along-track errors, when being validated in the Bluesky Air Traffic Simulator. The proposed model would significantly improve the performance of conflict detection systems where such trajectory prediction models are needed.
Highlights
Aircraft trajectory prediction is a crucial component of any air traffic control (ATC) system
The Adam optimizer, a variant of this method implemented in PyTorch, is selected to use in our experiment with learning rate set to 0.0001
The benchmark shows that our model performs significantly better and more stable than cLSTM does, in terms of Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) of latitude and longitude predictions
Summary
Aircraft trajectory prediction is a crucial component of any air traffic control (ATC) system. Aircraft trajectory is defined as “a four dimensional (e.g., latitude, longitude, altitude and time) description of an aircraft’s flight path” [1]. Trajectory prediction refers to the estimation of a flight’s future trajectory within a look-ahead time (prediction horizon) [1]. Accurate aircraft trajectory prediction improves situational awareness of air traffic control officers (ATCOs), and provides necessary inputs for other ATC functionalities such as departure and arrival management, monitoring aids, medium-term conflict detection (MTCD), short-term conflict alert (STCA), etc [2]. Improvement in the accuracy of trajectory prediction in the look-ahead time of approximately 4-8 minutes could potentially help to reduce STCA’s nuisance alerts, which in turns enhances the system overall efficiency.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
